© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15011
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their involvement in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.08
    2:0.10
    3:0.06
    4:0.03
    5:0.02
    6:0.14
    7:0.12
    8:0.01
    9:0.04
    10:0.16
    11:0.04
    Negative Logits
     ACE
    -3.27
    Chain
    -2.99
    obyl
    -2.97
     resil
    -2.88
     circ
    -2.74
     Caribbean
    -2.65
     Jamaica
    -2.65
     Liberia
    -2.58
     SAN
    -2.53
    Commission
    -2.52
    POSITIVE LOGITS
     Witt
    9.53
     Wiz
    3.75
     Wright
    3.41
     Berks
    3.29
     UW
    3.25
     Fowler
    3.18
     Wah
    3.15
     Patton
    3.08
    WP
    3.05
     Weber
    3.04
    Activations Density 0.001%

    No Known Activations